Hardware- and Vision-in-the-Loop Validation of Deep Monocular Pose Estimation for Autonomous Maritime UAV Flight

2026-06-17

AI Summary

This work addresses the challenge of validating autonomous shipboard UAV operations under realistic maritime conditions, which is typically hindered by high costs, safety risks, and environmental constraints. To bridge the gap between pure simulation and real-ship trials, the authors present a high-fidelity hardware-in-the-loop simulation framework that faithfully replicates dynamic sea environments indoors while preserving the perception latency and asynchrony inherent to embedded platforms. The system employs a deep Transformer-based monocular visual pose estimator, tightly fused with IMU measurements via a delayed Kalman filter to achieve robust state estimation. This pipeline drives a geometric controller enabling fully autonomous flight. Experimental results demonstrate stable takeoff, accurate trajectory tracking, and successful landing under computational constraints and perceptual delays, thereby establishing a critical validation intermediary between simulation and at-sea testing.

Abstract

Autonomous UAV operations on ships require reliable vision-based relative pose estimation, yet at-sea validation is costly, weather-dependent, and risky. This paper presents a hardware-validated vision-in-the-loop framework that enables fully autonomous indoor flight while emulating photorealistic maritime environments. Rendered maritime views are processed onboard by a deep transformer-based monocular pose estimator. Delayed vision measurements are fused with high-rate IMU data using a delayed Kalman filter to provide consistent state estimates for geometric control. The system captures critical embedded effects, including perception latency, asynchronous updates, and computational constraints, that are absent in pure simulation. Autonomous takeoff, trajectory tracking, and landing experiments demonstrate stable closed-loop flight. The results establish a safe and hardware-realistic intermediate stage for developing maritime UAV autonomy prior to shipboard deployment.

Problem

• autonomous maritime UAV
• monocular pose estimation
• vision-in-the-loop validation
• relative pose estimation
• at-sea validation

Innovation

• vision-in-the-loop
• monocular pose estimation
• delayed Kalman filter
• hardware-in-the-loop
• maritime UAV